diff --git a/modules/videos/test/test_transcode_job.py b/modules/videos/test/test_transcode_job.py index 2d5f7bed..65237773 100644 --- a/modules/videos/test/test_transcode_job.py +++ b/modules/videos/test/test_transcode_job.py @@ -1,4 +1,5 @@ """Tests for the transcode Job and its API (see `wrolpi.jobs`).""" +import hashlib import json import pathlib import shutil @@ -318,3 +319,41 @@ async def test_transcode_temp_file_is_not_discovered_by_refresh(test_session, te assert str(video_path) in primary_paths assert str(tmp_path) not in primary_paths, 'the transcoder temporary file was indexed' assert not any(str(tmp_path) in str(p) for p in primary_paths) + + +@pytest.mark.asyncio +@pytest.mark.parametrize('recorded', [True, False]) +async def test_transcode_video_job_refreshes_sha256(test_session, test_directory, async_client, video_factory, + recorded): + """The sums a download recorded follow the files the Job replaced; a Video without sums gains none.""" + video_path = test_directory / 'videos/NO CHANNEL/movie.webm' + video_path.parent.mkdir(parents=True, exist_ok=True) + wrolpi = {'custom_title': 'Mine'} + if recorded: + wrolpi['sha256'] = {'.webm': 'old webm', '.ffprobe.json': 'old ffprobe'} + video = video_factory(with_video_file=video_path, with_info_json={'duration': 5, 'wrolpi': wrolpi}) + test_session.commit() + info_json_path = video_path.with_suffix('.info.json') + + async def fake_run_command(cmd, stdout_callback=None, **kwargs): + if cmd[-1] == '-': + return CommandResult(return_code=0, cancelled=False, stdout=b'', stderr=b'', elapsed=0) + shutil.copy(PROJECT_DIR / 'test/big_buck_bunny_720p_1mb.mp4', cmd[-1]) + return CommandResult(return_code=0, cancelled=False, stdout=b'', stderr=b'', elapsed=1) + + with mock.patch('wrolpi.cmd.run_command', side_effect=fake_run_command): + job_id = transcode_video_job.enqueue(file_group_id=video.file_group_id, container='mp4') + record = await jobs.wait_for_job(job_id) + assert record['status'] == jobs.COMPLETE, record + + wrolpi = json.loads(info_json_path.read_text())['wrolpi'] + assert wrolpi['custom_title'] == 'Mine' + if not recorded: + assert 'sha256' not in wrolpi + return + mp4_path = video_path.with_suffix('.mp4') + ffprobe_json_path = video_path.with_suffix('.ffprobe.json') + assert wrolpi['sha256'] == { + '.mp4': hashlib.sha256(mp4_path.read_bytes()).hexdigest(), + '.ffprobe.json': hashlib.sha256(ffprobe_json_path.read_bytes()).hexdigest(), + } diff --git a/modules/videos/transcode.py b/modules/videos/transcode.py index a649381e..efc8b9c1 100644 --- a/modules/videos/transcode.py +++ b/modules/videos/transcode.py @@ -9,6 +9,7 @@ from wrolpi.captions import FFMPEG_BIN from wrolpi.cmd import run_command from wrolpi.common import logger, get_relative_to_media_directory, wrol_mode_enabled from wrolpi.db import get_db_session +from wrolpi.files.lib import sha256_files, sha256_by_suffix from wrolpi.jobs import register_job, get_current_job from wrolpi.vars import DEFAULT_FILE_PERMISSIONS, PYTEST @@ -505,6 +506,22 @@ def retarget_file_group(file_group_id: int, old_path: pathlib.Path, new_path: pa file_group.indexed = False +async def refresh_recorded_sha256(file_group_id: int): + """Hash a FileGroup's files again if a download recorded their sums; the recorded sums describe files which + may have been replaced. The files are read without a session held.""" + from wrolpi.files.models import FileGroup + + with get_db_session() as session: + file_group = session.get(FileGroup, file_group_id) + if 'sha256' not in file_group.get_wrolpi_json(): + return + paths = file_group.my_paths() + + sums = await asyncio.to_thread(sha256_files, paths) + with get_db_session(commit=True) as session: + session.get(FileGroup, file_group_id).update_wrolpi_json({'sha256': sha256_by_suffix(sums)}) + + @register_job('transcode_video') async def transcode_video_job(file_group_id: int, video_codec: Optional[str] = None, audio_codec: Optional[str] = None, container: str = 'mp4', @@ -543,4 +560,6 @@ async def transcode_video_job(file_group_id: int, video_codec: Optional[str] = N job_id = file_worker.queue_refresh([final_path], send_events=False) await file_worker.wait_for_job(job_id) + await refresh_recorded_sha256(file_group_id) + return {'path': str(get_relative_to_media_directory(final_path))}